Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM

TL;DR

Holmes-VAD introduces a multimodal, explainable video anomaly detection framework that leverages large-scale instruction tuning and rich annotations to improve bias mitigation and interpretability in detecting challenging or unseen events.

Contribution

The paper presents the first large-scale multimodal VAD instruction-tuning benchmark and a novel framework that enhances unbiasedness and interpretability in video anomaly detection.

Findings

Holmes-VAD achieves improved anomaly localization accuracy.

The framework provides comprehensive explanations for detections.

Benchmark and model are publicly available for community use.

Abstract

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi-automatic labeling paradigm. Efficient single-frame annotations are applied to the collected untrimmed videos, which are then synthesized into high-quality analyses of both abnormal and normal video clips using a robust off-the-shelf video captioner and a large language model (LLM). Building upon the VAD-Instruct50k dataset, we develop a customized solution for interpretable video anomaly detection. We train a lightweight temporal sampler to select frames with high anomaly response and fine-tune a multimodal large language model (LLM) to generate explanatory content. Extensive experimental results validate the generality and interpretability of the proposed Holmes-VAD, establishing it as a novel interpretable technique for real-world video anomaly analysis. To support the community, our benchmark and model will be publicly available at https://holmesvad.github.io.